SpecTune improves LLM-based automated program repair by validating localized postconditions and using their intermediate violations for more precise fault localization and patching.
Less training, more repairing please: revisiting automated program repair via zero-shot learning
9 Pith papers cite this work, alongside 63 external citations. Polarity classification is still indexing.
9
Pith papers citing it
63
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Unified multi-language deep learning model for on-the-fly syntax highlighting using normalization and few-shot learning to support six languages with lower deployment cost.
Transformer RL with a Policy Model and Action Sampler finds UTM safety vulnerabilities 8x more efficiently than expert testing in 700-hour simulations.
An empirical study finds that injecting call/inheritance topology as comments improves LLM code agent localization by 2.2pp, shortens trajectories by 1.6 rounds, and halves run-to-run variance on medium repositories via a deterministic anchoring effect.
Multi-stage LLM training plus compiler-guided error repair boosts functional equivalence in Java-to-Cangjie translation by 6.06% over prior methods despite scarce parallel data.
AdaDec improves Pass@1 accuracy of LLM code generation by up to 20.9% over greedy decoding by triggering lookahead reranking only at high-uncertainty steps on HumanEval+, MBPP+, and DevEval.
RADAR automates review of 331K+ low-risk diffs at Meta with 1/3 the revert rate and 1/50 the production incident rate of non-RADAR diffs, while reducing median close time by over 330%.
A research roadmap analyzing the current state of search-based software engineering with foundation models, outlining challenges and directions across three integration aspects.
citing papers explorer
-
Enhancing Program Repair with Specification Guidance and Intermediate Behavioral Signals
SpecTune improves LLM-based automated program repair by validating localized postconditions and using their intermediate violations for more precise fault localization and patching.
-
Multi Language Models for On-the-Fly Syntax Highlighting
Unified multi-language deep learning model for on-the-fly syntax highlighting using normalization and few-shot learning to support six languages with lower deployment cost.
-
Revealing Safety-Critical Scenarios for UTM via Transformer
Transformer RL with a Policy Model and Action Sampler finds UTM safety vulnerabilities 8x more efficiently than expert testing in 700-hour simulations.
-
How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring
An empirical study finds that injecting call/inheritance topology as comments improves LLM code agent localization by 2.2pp, shortens trajectories by 1.6 rounds, and halves run-to-run variance on medium repositories via a deterministic anchoring effect.
-
Boosting Automatic Java-to-Cangjie Translation with Multi-Stage LLM Training and Error Repair
Multi-stage LLM training plus compiler-guided error repair boosts functional equivalence in Java-to-Cangjie translation by 6.06% over prior methods despite scarce parallel data.
-
AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation
AdaDec improves Pass@1 accuracy of LLM code generation by up to 20.9% over greedy decoding by triggering lookahead reranking only at high-uncertainty steps on HumanEval+, MBPP+, and DevEval.
-
Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency
RADAR automates review of 331K+ low-risk diffs at Meta with 1/3 the revert rate and 1/50 the production incident rate of non-RADAR diffs, while reducing median close time by over 330%.
-
Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap
A research roadmap analyzing the current state of search-based software engineering with foundation models, outlining challenges and directions across three integration aspects.
- AgentModernize: Preserving Business Logic in Legacy Modernization with Multi-Agent LLMs and Behavioral Specification Graphs